Alternatives and similar repositories for emergent-misalignment

Users that are interested in emergent-misalignment are comparing it to the libraries listed below

• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆220Updated last year
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆164Updated 7 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆311Updated 5 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆297Updated last week
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆515Updated last week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆130Updated 9 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆248Updated last year
• safety-research / persona_vectors
  Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  ☆304Updated 4 months ago
• METR / task-standard
  METR Task Standard
  ☆168Updated 10 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆231Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆232Updated 11 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆122Updated last year
• goodfire-ai / scribe
  ☆54Updated 2 months ago
• google-deepmind / mishax
  ☆144Updated 3 months ago
• METR / public-tasks
  ☆108Updated 3 weeks ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆134Updated this week
• anthropic-experimental / agentic-misalignment
  ☆533Updated 5 months ago
• haizelabs / bijection-learning
  ☆26Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆196Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆284Updated last year
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆670Updated last week
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆151Updated 5 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆120Updated last month
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆322Updated last month
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆302Updated 11 months ago
• METR / RE-Bench
  ☆119Updated last month
• google-deepmind / dangerous-capability-evaluations
  ☆62Updated 2 months ago
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆234Updated 4 months ago
• princeton-pli / hal-harness
  ☆200Updated last week
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆100Updated 2 years ago